Overview
Eligibility criteria for cancer drug trials are generally too stringent, leading to key issues such as low enrolment rates and lack of population diversity. In order to evaluate the REC of NSCLC drug trials, this study will use deep learning methods to construct a structured real-world database of NSCLC across dimensions, and quantitatively assess the independent contribution of changes in each eligibility criterion to patient numbers, clinical efficacy and safety.
Description
Restrictive eligibility criteria in cancer drug trials result in low enrollment rates and limited population diversity. Relaxed eligibility criteria (REC) based on solid evidence is becoming necessary for stakeholders worldwide. However, the absence of high-quality, favorable evidence remains a major challenge. This study presents a protocol to quantitatively evaluate the impact of relaxing eligibility criteria in common non-small cell lung cancer (NSCLC) protocols in China, on the risk-benefit profile. This involves a detailed explanation of the rationale, framework, and design of REC.
To evaluate our REC in NSCLC drug trials, we will first construct a structured, cross-dimensional real-world NSCLC database using deep learning methods. We will then establish randomized virtual cohorts and perform benefit-risk assessment using Monte Carlo simulation and propensity matching. Shapley value will be utilized to quantitatively measure the effect of the change of each eligibility criterion on patient volume, clinical efficacy and safety.
Eligibility
Inclusion Criteria:
Patients in the database were considered to be part of the real-world cohort if they were
(1) diagnosed with NSCLC according to the tenth revision of the international
classification of diseases (ICD-10) code; (2) diagnosed with stage IIIB, IIIC, IV NSCLC
between 1 January 2013 and 31 December, 2022; (3) had at least two documented clinical
visits on or after 1 January 2013.
Exclusion Criteria:
（1）NSCLC in stage I-IIIa